Descriptives across the categories (Political_True and _False AND COVID_True and _False)
df_political %>% group_by(Category, measurement) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 9
## # Groups: Category [4]
## Category measurement mean SD count se median min max
## <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl>
## 1 COVID_Fake Acc_Abs 51.0 12.6 60 1.63 51.5 14.3 77.1
## 2 COVID_Fake Acc 3.22 0.500 60 0.0646 3.16 2.08 4.88
## 3 COVID_Fake Fam 2.15 0.267 60 0.0345 2.08 1.52 2.84
## 4 COVID_True Acc_Abs 66.7 11.8 98 1.19 67.8 30.2 84.8
## 5 COVID_True Acc 3.93 0.484 98 0.0489 3.99 2.6 4.81
## 6 COVID_True Fam 2.51 0.449 98 0.0453 2.47 1.58 4.12
## 7 Political_Fake Acc_Abs 57.7 13.4 140 1.13 58.8 21.9 85.4
## 8 Political_Fake Acc 2.96 0.536 140 0.0453 2.90 1.8 4.42
## 9 Political_Fake Fam 2.03 0.305 140 0.0258 2.02 1.29 3.51
## 10 Political_True Acc_Abs 63.1 12.5 152 1.01 64.9 25.7 88.2
## 11 Political_True Acc 3.79 0.505 152 0.0410 3.82 2.14 4.82
## 12 Political_True Fam 2.42 0.414 152 0.0336 2.33 1.7 3.61
# Basic histogram Absolute Accuracy
df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For all values collapsed across political leaning and items") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic boxplot Absolute Accuracy
df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_boxplot() + theme_apa() + labs(title = "Accuracy Boxplot - Percentage", x = "Percentage Values", y = "Count", subtitle = "For all values collapsed across political leaning and items")

# Basic histogram Absolute Accuracy
df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "Grouped by all categories, collapsed acorss political leaning") + facet_wrap(~Category)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic boxplot Absolute Accuracy
df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_boxplot() + theme_apa() + labs(title = "Accuracy Boxplot - Percentage", x = "Percentage Values", y = "Count", subtitle = "For all values collapsed across political leaning and true vs false news") + facet_wrap(~Category)

# Basic histogram Relative Accuracy
df_political %>% filter(measurement == "Acc") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For all values collapsed across political leaning and items \n 1: extremely unlikely; 6 extremely likely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
df_political %>% filter(measurement == "Acc") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "Collapsed acorss political leaning \n 1: extremely unlikely; 6 extremely likely") + facet_wrap(~Category)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
df_political %>% filter(measurement == "Fam") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For all values collapsed across political leaning and items \n 1: not at all; 6 extremely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
df_political %>% filter(measurement == "Fam") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "Collapsed acorss political leaning \n 1: not at all; 6 extremely") + facet_wrap(~Category)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Descriptives across the _True only
df_political_true %>% group_by(Category, political_leaning, measurement) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 10
## # Groups: Category, political_leaning [4]
## Category political_leani… measurement mean SD count se median
## <chr> <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl>
## 1 COVID_T… Democrat Acc_Abs 70.2 10.2 49 1.45 72.9
## 2 COVID_T… Democrat Acc 4.13 0.443 49 0.0633 4.21
## 3 COVID_T… Democrat Fam 2.62 0.469 49 0.0670 2.53
## 4 COVID_T… Republican Acc_Abs 63.2 12.3 49 1.76 64.4
## 5 COVID_T… Republican Acc 3.73 0.445 49 0.0635 3.76
## 6 COVID_T… Republican Fam 2.41 0.405 49 0.0579 2.41
## 7 Politic… Democrat Acc_Abs 66.2 11.6 76 1.33 68.5
## 8 Politic… Democrat Acc 3.94 0.459 76 0.0526 3.98
## 9 Politic… Democrat Fam 2.45 0.458 76 0.0526 2.3
## 10 Politic… Republican Acc_Abs 60.0 12.6 76 1.45 58.2
## 11 Politic… Republican Acc 3.65 0.512 76 0.0587 3.61
## 12 Politic… Republican Fam 2.39 0.364 76 0.0418 2.34
## # … with 2 more variables: min <dbl>, max <dbl>
# Basic histogram Absolute Accuracy
df_political_true %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _True only, collapsed across political leaning") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Absolute Accuracy
df_political_true %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _True only") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
df_political_true %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only, collapsed across political leaning \n 1: extremely unlikely; 6 extremely likely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
df_political_true %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only \n 1: extremely unlikely; 6 extremely likely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
df_political_true %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only, collapsed across political leaning \n 1: not at all; 6 extremely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
df_political_true %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only \n 1: not at all; 6 extremely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Descriptives across the _False only
df_political_false %>% group_by(Category, political_leaning, measurement) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 10
## # Groups: Category, political_leaning [4]
## Category political_leani… measurement mean SD count se median
## <chr> <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl>
## 1 COVID_F… Democrat Acc_Abs 53.3 13.1 30 2.39 56.6
## 2 COVID_F… Democrat Acc 3.13 0.536 30 0.0979 3.04
## 3 COVID_F… Democrat Fam 2.07 0.246 30 0.0448 2.04
## 4 COVID_F… Republican Acc_Abs 48.7 11.9 30 2.17 47.8
## 5 COVID_F… Republican Acc 3.31 0.452 30 0.0825 3.31
## 6 COVID_F… Republican Fam 2.23 0.267 30 0.0488 2.22
## 7 Politic… Democrat Acc_Abs 58.8 12.7 70 1.52 59.5
## 8 Politic… Democrat Acc 2.94 0.515 70 0.0615 2.92
## 9 Politic… Democrat Fam 2.05 0.322 70 0.0385 2.02
## 10 Politic… Republican Acc_Abs 56.7 14.1 70 1.68 58.7
## 11 Politic… Republican Acc 2.98 0.560 70 0.0670 2.90
## 12 Politic… Republican Fam 2.01 0.289 70 0.0345 1.96
## # … with 2 more variables: min <dbl>, max <dbl>
# Basic histogram Absolute Accuracy
df_political_false %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _False only, collapsed across political leaning") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Absolute Accuracy
df_political_false %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _False only") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
df_political_false %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only, collapsed across political leaning \n 1: extremely unlikely; 6 extremely likely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
df_political_false %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only \n 1: extremely unlikely; 6 extremely likely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
df_political_false %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only, collapsed across political leaning \n 1: not at all; 6 extremely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
df_political_false %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only \n 1: not at all; 6 extremely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Clean Descriptives across the categories (Political_True and _False)
c_df_political %>% group_by(Category, measurement) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 9
## # Groups: Category [4]
## Category measurement mean SD count se median min max
## <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl>
## 1 COVID_Fake Acc_Abs 53.2 10.6 54 1.45 53.3 32.7 77.1
## 2 COVID_Fake Acc 3.14 0.429 54 0.0583 3.15 2.08 3.96
## 3 COVID_Fake Fam 2.14 0.267 54 0.0364 2.08 1.52 2.84
## 4 COVID_True Acc_Abs 68.3 10.1 92 1.05 68.7 42.9 84.8
## 5 COVID_True Acc 3.99 0.424 92 0.0442 4.02 2.95 4.81
## 6 COVID_True Fam 2.55 0.433 92 0.0451 2.50 1.58 4.12
## 7 Political_Fake Acc_Abs 58.5 11.5 126 1.03 59.1 33.3 78.3
## 8 Political_Fake Acc 2.93 0.459 126 0.0409 2.90 1.94 3.89
## 9 Political_Fake Fam 2.02 0.272 126 0.0243 2.01 1.29 2.75
## 10 Political_True Acc_Abs 64.6 10.7 134 0.923 65.8 42.9 87.0
## 11 Political_True Acc 3.85 0.439 134 0.0380 3.86 2.88 4.82
## 12 Political_True Fam 2.46 0.412 134 0.0356 2.35 1.7 3.61
# Basic histogram Absolute Accuracy
c_df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For all values collapsed across political leaning and items") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic boxplot Absolute Accuracy
c_df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_boxplot() + theme_apa() + labs(title = "Accuracy Boxplot - Percentage", x = "Percentage Values", y = "Count", subtitle = "For all values collapsed across political leaning and items")

# Basic histogram Absolute Accuracy
c_df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "Grouped by all categories, collapsed acorss political leaning") + facet_wrap(~Category)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic boxplot Absolute Accuracy
c_df_political %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value)) + geom_boxplot() + theme_apa() + labs(title = "Accuracy Boxplot - Percentage", x = "Percentage Values", y = "Count", subtitle = "For all values collapsed across political leaning and items") + facet_wrap(~Category)

# Basic histogram Relative Accuracy
c_df_political %>% filter(measurement == "Acc") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For all values collapsed across political leaning and items \n 1: extremely unlikely; 6 extremely likely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
c_df_political %>% filter(measurement == "Acc") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "Collapsed acorss political leaning \n 1: extremely unlikely; 6 extremely likely") + facet_wrap(~Category)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
c_df_political %>% filter(measurement == "Fam") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For all values collapsed across political leaning and items \n 1: not at all; 6 extremely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
c_df_political %>% filter(measurement == "Fam") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "Collapsed acorss political leaning \n 1: not at all; 6 extremely") + facet_wrap(~Category)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Clean Descriptives across the _True only
c_df_political_true %>% group_by(Category, political_leaning, measurement) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 10
## # Groups: Category, political_leaning [4]
## Category political_leani… measurement mean SD count se median
## <chr> <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl>
## 1 COVID_T… Democrat Acc_Abs 71.7 8.35 46 1.23 73.8
## 2 COVID_T… Democrat Acc 4.19 0.376 46 0.0554 4.21
## 3 COVID_T… Democrat Fam 2.66 0.455 46 0.0671 2.55
## 4 COVID_T… Republican Acc_Abs 64.9 10.6 46 1.56 65.3
## 5 COVID_T… Republican Acc 3.80 0.378 46 0.0558 3.84
## 6 COVID_T… Republican Fam 2.45 0.387 46 0.0570 2.42
## 7 Politic… Democrat Acc_Abs 67.3 10.5 67 1.28 68.9
## 8 Politic… Democrat Acc 3.98 0.410 67 0.0501 4
## 9 Politic… Democrat Fam 2.49 0.459 67 0.0561 2.32
## 10 Politic… Republican Acc_Abs 61.9 10.3 67 1.26 58.8
## 11 Politic… Republican Acc 3.73 0.434 67 0.0530 3.65
## 12 Politic… Republican Fam 2.43 0.361 67 0.0441 2.36
## # … with 2 more variables: min <dbl>, max <dbl>
# Basic histogram Absolute Accuracy
c_df_political_true %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _True only, collapsed across political leaning") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Absolute Accuracy
c_df_political_true %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _True only") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
c_df_political_true %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only, collapsed across political leaning \n 1: extremely unlikely; 6 extremely likely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
c_df_political_true %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only \n 1: extremely unlikely; 6 extremely likely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
c_df_political_true %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only, collapsed across political leaning \n 1: not at all; 6 extremely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
c_df_political_true %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _True only \n 1: not at all; 6 extremely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Clean Descriptives across the Political_False only
c_df_political_false %>% group_by(Category, political_leaning, measurement) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 10
## # Groups: Category, political_leaning [4]
## Category political_leani… measurement mean SD count se median
## <chr> <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl>
## 1 COVID_F… Democrat Acc_Abs 55.9 9.86 27 1.90 57.1
## 2 COVID_F… Democrat Acc 3.04 0.415 27 0.0799 3
## 3 COVID_F… Democrat Fam 2.04 0.223 27 0.0429 2.04
## 4 COVID_F… Republican Acc_Abs 50.5 10.9 27 2.09 48.8
## 5 COVID_F… Republican Acc 3.24 0.424 27 0.0817 3.26
## 6 COVID_F… Republican Fam 2.25 0.271 27 0.0521 2.25
## 7 Politic… Democrat Acc_Abs 58.7 11.5 63 1.45 58.5
## 8 Politic… Democrat Acc 2.94 0.461 63 0.0581 2.93
## 9 Politic… Democrat Fam 2.03 0.277 63 0.0348 2.02
## 10 Politic… Republican Acc_Abs 58.2 11.6 63 1.46 59.3
## 11 Politic… Republican Acc 2.92 0.460 63 0.0580 2.86
## 12 Politic… Republican Fam 2.00 0.269 63 0.0339 1.95
## # … with 2 more variables: min <dbl>, max <dbl>
# Basic histogram Absolute Accuracy
c_df_political_false %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _False only, collapsed across political leaning") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Absolute Accuracy
c_df_political_false %>% filter(measurement == "Acc_Abs") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Percentage", x = "Percentage Values", y = "Count", subtitle = "For _False only") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
c_df_political_false %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only, collapsed across political leaning \n 1: extremely unlikely; 6 extremely likely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Relative Accuracy
c_df_political_false %>% filter(measurement == "Acc") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Accuracy Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only \n 1: extremely unlikely; 6 extremely likely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
c_df_political_false %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only, collapsed across political leaning \n 1: not at all; 6 extremely") + geom_vline(aes(xintercept = mean(value)), linetype="dashed")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram Familiarity
c_df_political_false %>% filter(measurement == "Fam") %>% ggplot(aes(x=value, fill = Category)) + geom_histogram() + theme_apa() + labs(title = "Familiarity Histogram - Likert means", x = "Likert Values", y = "Count", subtitle = "For _False only \n 1: not at all; 6 extremely") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Item selection (politically true only)
all items, no familiarity thershold (political_true only)
#all familiarity
c_df_political_true %>% filter(measurement == "Fam") %>%
ggplot() + geom_bar(aes(x = `Image Name`, y = value, fill = Par_Combined), stat = 'identity', position = 'dodge') + theme_apa(legend.use.title = TRUE) + theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 4)) + labs(title = "All items, all familiarity", x = "Image Name", y = "Familiarity", fill = "Item Pol. Leaning") + scale_fill_manual(values=c("#0021F5", "#EA3223"))

accuracy_all_fam <- c_df_political_true %>% filter(measurement == "Acc_Abs") %>% group_by(political_leaning, Par_Combined) %>% summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
accuracy_all_fam
## # A tibble: 4 x 9
## # Groups: political_leaning [2]
## political_leaning Par_Combined mean SD count se median min max
## <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl>
## 1 Democrat Dem Favoured 70.9 8.70 79 0.979 72 45.1 85
## 2 Democrat Rep Favoured 64.8 11.1 34 1.91 66.0 44.6 86.3
## 3 Republican Dem Favoured 61.2 10.1 79 1.13 58.5 42.9 87.0
## 4 Republican Rep Favoured 67.5 10.2 34 1.74 67.6 42.9 84.8
accuracy_all_fam <- c_df_political_true %>% filter(measurement == "Acc_Abs") %>% group_by(Category, political_leaning, Par_Combined) %>% summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
accuracy_all_fam
## # A tibble: 8 x 10
## # Groups: Category, political_leaning [4]
## Category political_leani… Par_Combined mean SD count se median
## <chr> <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl>
## 1 COVID_T… Democrat Dem Favoured 73.3 7.64 32 1.35 75.3
## 2 COVID_T… Democrat Rep Favoured 68.0 9.03 14 2.41 66.0
## 3 COVID_T… Republican Dem Favoured 63.9 10.2 32 1.81 63.9
## 4 COVID_T… Republican Rep Favoured 67.1 11.5 14 3.07 67.6
## 5 Politic… Democrat Dem Favoured 69.3 9.09 47 1.33 70.6
## 6 Politic… Democrat Rep Favoured 62.5 12.1 20 2.70 64.7
## 7 Politic… Republican Dem Favoured 59.4 9.64 47 1.41 56.8
## 8 Politic… Republican Rep Favoured 67.8 9.44 20 2.11 66.8
## # … with 2 more variables: min <dbl>, max <dbl>
#making table
# accuracy_all_fam_table <- accuracy_all_fam[1:4,-1]
accuracy_all_fam %>%
ggplot(aes(x = Par_Combined, y = mean, fill = as.factor(political_leaning))) +
geom_bar(stat = 'identity', position = 'dodge') + theme_apa(legend.use.title = TRUE) + labs(title ="Accuracy across Dem and Rep favoured items", x = "Item Political Leaning", y = "Percent Accuracy", fill = "Pps Political Leaning") + scale_fill_manual(values=c("#0021F5", "#EA3223"))

accuracy_all_fam %>%
ggplot(aes(x = Par_Combined, y = mean, fill = as.factor(political_leaning))) +
geom_bar(stat = 'identity', position = 'dodge') + geom_errorbar(aes(ymin = mean-se, ymax =mean + se), width = .2, position = position_dodge(.9)) + theme_apa(legend.use.title = TRUE) + labs(title ="Accuracy across Dem and Rep favoured items", x = "Item Political Leaning", y = "Percent Accuracy", fill = "Pps Political Leaning") + scale_fill_manual(values=c("#0021F5", "#EA3223")) + facet_wrap(~Category)

Item selection (politically false only)
all items, no familiarity thershold (political_false only)
#all familiarity
c_df_political_false %>% filter(measurement == "Fam") %>%
ggplot() + geom_bar(aes(x = `Image Name`, y = value, fill = Par_Combined), stat = 'identity', position = 'dodge') + theme_apa(legend.use.title = TRUE) + theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 4)) + labs(title = "All items, all familiarity", x = "Image Name", y = "Familiarity", fill = "Item Pol. Leaning") + scale_fill_manual(values=c("#0021F5", "#EA3223"))

accuracy_all_fam <- c_df_political_false %>% filter(measurement == "Acc_Abs") %>% group_by(political_leaning, Par_Combined) %>% summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
accuracy_all_fam
## # A tibble: 4 x 9
## # Groups: political_leaning [2]
## political_leaning Par_Combined mean SD count se median min max
## <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl>
## 1 Democrat Dem Favoured 54.3 11.7 44 1.77 55.2 34.0 77.1
## 2 Democrat Rep Favoured 61.3 9.30 46 1.37 60.1 41.9 78.3
## 3 Republican Dem Favoured 60.9 10.5 44 1.58 61.6 42.2 78.1
## 4 Republican Rep Favoured 51.2 11.2 46 1.66 53.3 32.7 73.5
accuracy_all_fam <- c_df_political_false %>% filter(measurement == "Acc_Abs") %>% group_by(Category, political_leaning, Par_Combined) %>% summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
accuracy_all_fam
## # A tibble: 8 x 10
## # Groups: Category, political_leaning [4]
## Category political_leani… Par_Combined mean SD count se median
## <chr> <chr> <fct> <dbl> <dbl> <int> <dbl> <dbl>
## 1 COVID_F… Democrat Dem Favoured 54.8 14.1 12 4.08 52.8
## 2 COVID_F… Democrat Rep Favoured 56.7 4.68 15 1.21 57.1
## 3 COVID_F… Republican Dem Favoured 56.0 10.6 12 3.05 53.7
## 4 COVID_F… Republican Rep Favoured 46.2 9.26 15 2.39 46.2
## 5 Politic… Democrat Dem Favoured 54.1 11.0 32 1.94 55.2
## 6 Politic… Democrat Rep Favoured 63.5 10.2 31 1.83 65.2
## 7 Politic… Republican Dem Favoured 62.7 10.0 32 1.77 63.2
## 8 Politic… Republican Rep Favoured 53.6 11.4 31 2.05 56.1
## # … with 2 more variables: min <dbl>, max <dbl>
accuracy_all_fam %>%
ggplot(aes(x = Par_Combined, y = mean, fill = as.factor(political_leaning))) +
geom_bar(stat = 'identity', position = 'dodge') + theme_apa(legend.use.title = TRUE) + labs(title ="Accuracy across Dem and Rep favoured items", x = "Item Political Leaning", y = "Percent Accuracy", fill = "Pps Political Leaning") + scale_fill_manual(values=c("#0021F5", "#EA3223"))

accuracy_all_fam %>%
ggplot(aes(x = Par_Combined, y = mean, fill = as.factor(political_leaning))) +
geom_bar(stat = 'identity', position = 'dodge') + geom_errorbar(aes(ymin = mean-se, ymax =mean + se), width = .2, position = position_dodge(.9)) + theme_apa(legend.use.title = TRUE) + labs(title ="Accuracy across Dem and Rep favoured items", x = "Item Political Leaning", y = "Percent Accuracy", fill = "Pps Political Leaning") + scale_fill_manual(values=c("#0021F5", "#EA3223")) + facet_wrap(~Category)

# final selection
# View(c_df_political_true %>% filter(measurement == "Fam", Par_Combined == "Dem Favoured", political_leaning == "Democrat"))
tmp <- c_df_political_true %>% filter(measurement == "Fam", Par_Combined == "Dem Favoured", political_leaning == "Democrat")
tmp <- rbind(tmp, c_df_political_true %>% filter(measurement == "Fam", Par_Combined == "Rep Favoured", political_leaning == "Democrat"))
tmp <- rbind(tmp, c_df_political_false %>% filter(measurement == "Fam", Par_Combined == "Dem Favoured", political_leaning == "Democrat"))
tmp <- rbind(tmp, c_df_political_false %>% filter(measurement == "Fam", Par_Combined == "Rep Favoured", political_leaning == "Democrat"))
write_xlsx(
tmp,
path = "item_selection - review(1).xlsx",
col_names = TRUE)
Partisian
# removing unnecessary columns
df_slim_leaning <- df[, c("Item #", "Category", "Image Name", "Headline Summary", "Par_Dem", "Par_Rep", "Par_Combined")]
#add whether the items are democratic favoured or republican favoured
df_slim_leaning$Par_Combined_Categ <- ifelse(df_slim_leaning$Par_Combined > 3.5, "Rep Favoured", "Dem Favoured")
# long format
df_slim_leaning_long <- gather(df_slim_leaning, key = "measurement", value = "value", -c("Item #", "Category", "Image Name", "Headline Summary", "Par_Combined_Categ"))
# adding political variable
df_slim_leaning_long$political_leaning <- "Democrat"
df_slim_leaning_long$political_leaning <- ifelse(str_detect(df_slim_leaning_long$measurement, "Rep") == TRUE, df_slim_leaning_long$political_leaning <- "Republican", df_slim_leaning_long$political_leaning <- "Democrat")
df_slim_leaning_long$political_leaning[str_detect(df_slim_leaning_long$measurement, "Combined")] <- "Combined"
df_slim_leaning_long$Par_Combined_Categ[str_detect(df_slim_leaning_long$measurement, "Combined")] <- "Combined"
df_slim_leaning_long$measurement <- str_replace(df_slim_leaning_long$measurement, c("_Rep"), "")
df_slim_leaning_long$measurement <- str_replace(df_slim_leaning_long$measurement, c("_Dem"), "")
df_slim_leaning_long$measurement <- str_replace(df_slim_leaning_long$measurement, c("_Combined"), "")
#adding classes
df_slim_leaning_long$Par_Combined_Categ <- factor(df_slim_leaning_long$Par_Combined_Categ, levels = c("Dem Favoured", "Rep Favoured", "Combined"))
# df_slim_leaning_long <- df_slim_leaning_long %>% filter(Category == "Political_True" | Category == "Political_Fake")
# removing those high or low in accuracy
# after identifying which items to remove now creating new corrected dfs
df_slim_leaning_long <- df_slim_leaning_long %>% filter(`Item #` %notin% index_remove_all)
df_slim_leaning_long %>% group_by(Category, political_leaning) %>%
summarise(mean = mean(value), SD = sd(value), count = n(), se = (SD/(sqrt(count))), median = median(value), min = min(value), max = max(value))
## # A tibble: 12 x 9
## # Groups: Category [4]
## Category political_leani… mean SD count se median min max
## <chr> <chr> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <dbl>
## 1 COVID_Fake Combined 3.54 0.359 27 0.0691 3.54 2.95 4.60
## 2 COVID_Fake Democrat 3.32 0.387 27 0.0746 3.29 2.54 4.46
## 3 COVID_Fake Republican 3.77 0.404 27 0.0777 3.83 3.1 4.73
## 4 COVID_True Combined 3.23 0.412 46 0.0607 3.24 2.49 3.97
## 5 COVID_True Democrat 2.89 0.378 46 0.0557 2.91 2.13 3.6
## 6 COVID_True Republican 3.57 0.527 46 0.0777 3.52 2.7 4.73
## 7 Political_… Combined 3.44 0.579 63 0.0730 3.34 2.26 4.50
## 8 Political_… Democrat 3.25 0.566 63 0.0713 3.24 2.12 4.3
## 9 Political_… Republican 3.64 0.637 63 0.0803 3.6 2.19 4.82
## 10 Political_… Combined 3.23 0.529 67 0.0646 3.13 2.31 4.50
## 11 Political_… Democrat 2.98 0.524 67 0.0640 2.9 2.07 4.07
## 12 Political_… Republican 3.47 0.613 67 0.0749 3.39 2.17 5.15
# Basic histogram partisanship combined
df_slim_leaning_long %>% filter(political_leaning == "Combined") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - Combined", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + geom_vline(aes(xintercept = mean(value)), linetype="dashed") + ylim(0,18)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram partisanship combined facet
df_slim_leaning_long %>% filter(political_leaning == "Combined") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - Combined", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + facet_wrap(~Category) + ylim(0,18)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram partisanship dems only
df_slim_leaning_long %>% filter(political_leaning == "Democrat") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - Democrats Only", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + geom_vline(aes(xintercept = mean(value)), linetype="dashed") + ylim(0,18)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram partisanship dems only facet
df_slim_leaning_long %>% filter(political_leaning == "Democrat") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - Democrats Only", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + facet_wrap(~Category) + ylim(0,18)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram partisanship reps
df_slim_leaning_long %>% filter(political_leaning == "Republican") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - Republicans Only", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + geom_vline(aes(xintercept = mean(value)), linetype="dashed") + ylim(0,18)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram partisanship reps facet
df_slim_leaning_long %>% filter(political_leaning == "Republican") %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - Republicans Only", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + facet_wrap(~Category) + ylim(0,18)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# Basic histogram all partisanship factors
df_slim_leaning_long %>% ggplot(aes(x=value)) + geom_histogram() + theme_apa() + labs(title = "Partisanship - All factors", x = "Likert Values", y = "Count", subtitle = "If accurate, how favorable to Democrats vs. Republicans (>= 4: Rep)") + facet_wrap(~political_leaning)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
